Lythri-Tada-4B is part of the Lythri 2.0 family, with 4.63B total parameters and 2.3B activated parameters. It answers directly without a thinking phase, while reinforce model's emotional understanding.
Compared with the previous-generation Lythri-4B-A2B, Tada brings three main upgrades:
Stronger instruction following. Tada scores 39.19 on IFEval (prompt-level strict), surpassing even the Lythri-7B-A4B (31.05).
Better multi-turn conversations. Tada keeps track of earlier context and user requests more consistently over long chats, and carries the emotional thread from turn to turn.
System prompt support. Unlike Lythri-4B-A2B, Tada follows system prompts, so you can set a persona, tone or rules for your app directly in the system message.
Long-tail knowledge, such as graduate-level science questions, is slightly weaker than Lythri-4B-A2B, while overall performance improves substantially.
On the EQ-Bench Slop Score, which measures how much a model relies on typical AI phrasing (lower is better), Lythri-Tada-4B scores 39.0 and writes more naturally than GPT-4o (47.7) and DeepSeek-R1 (67.9), far ahead of Qwen3-4B (62.2) and Gemma-3-4B (85.2).
All benchmarks are evaluated with their official standard settings and the chat template applied, reflecting real-world inference conditions. Lythri-4B-A2B is evaluated with thinking; Lythri-Tada-4B answers directly without thinking.
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_path = "Lythri/Lythri-Tada-4B"
tok = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path, dtype=torch.bfloat16, device_map="auto"
)
messages = [{"role": "user", "content": "My friend just lost their job and seems really down. What should I say to them?"}]
chat = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tok(chat, return_tensors="pt", add_special_tokens=False).to(model.device)
with torch.inference_mode():
out = model.generate(
**inputs,
max_new_tokens=1024,
do_sample=True,
temperature=0.8,
top_p=0.95,
eos_token_id=[1, 106],
)
print(tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
Lythri-Tada-4B supports system prompts, which Lythri-4B-A2B does not. It works well without one; to set a persona or rules for your app, add a system message:
messages = [
{"role": "system", "content": "You are Lythri, a warm and caring companion. Reply in the same language as the user."},
{"role": "user", "content": "I had a really rough day at work."},
]
Lythri-Tada-4B starts from the Gemma4-E2B PT and training on SFT with CoT, followed by instant-reply SFT with multi-turn companion conversations, and online preference optimization on only writing with responses judged by Gemma2-27B.
Lythri is optimized for conversation and emotional understanding, not for math, coding or complex reasoning.
Lythri is not a substitute for professional mental health support. If you or someone you know is in crisis, please contact local emergency services or a crisis helpline.
Like all language models, it can produce inaccurate or inappropriate content.
import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("Lythri/Lythri-Tada-4B", revision="b0ffe8ec4dc17dac60858e5da687f4724fe1f09b")
model = AutoModelForCausalLM.from_pretrained("Lythri/Lythri-Tada-4B", revision="b0ffe8ec4dc17dac60858e5da687f4724fe1f09b", device_map="auto")
